PET Rapid Image Reconstruction Challenge (PETRIC)

2025-11-27

AI Summary

PET image reconstruction algorithms suffer from high computational cost and a lack of standardized, reproducible evaluation protocols. Method: We launched the first global PET reconstruction algorithm challenge, introducing an open-source, reproducible evaluation framework that integrates multi-source phantom datasets, a cross-device/cross-radiotracer benchmarking protocol, and a unified objective function. The framework incorporates preconditioned optimization, stochastic gradient methods, and AI techniques to enable automated performance quantification. Contribution/Results: Nine algorithms submitted by four teams exhibited substantial variation in reconstruction quality and runtime efficiency, validating the framework’s effectiveness, robustness, and scalability. This work establishes the first systematic, community-driven benchmark for PET reconstruction algorithms, filling a critical gap in the field and laying the foundation for future challenges and the development of low-latency, high-performance reconstruction methods.

Technology Category

• Search and Optimization: Algorithm Configuration
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Introduction: We describe the foundation of PETRIC, an image reconstruction challenge to minimise the computational runtime of related algorithms for Positron Emission Tomography (PET). Purpose: Although several similar challenges are well-established in the field of medical imaging, there have been no prior challenges for PET image reconstruction. Methods: Participants are provided with open-source software for implementation of their reconstruction algorithm(s). We define the objective function and reconstruct "gold standard" reference images, and provide metrics for quantifying algorithmic performance. We also received and curated phantom datasets (acquired with different scanners, radionuclides, and phantom types), which we further split into training and evaluation datasets. The automated computational framework of the challenge is released as open-source software. Results: Four teams with nine algorithms in total participated in the challenge. Their contributions made use of various tools from optimisation theory including preconditioning, stochastic gradients, and artificial intelligence. While most of the submitted approaches appear very similar in nature, their specific implementation lead to a range of algorithmic performance. Conclusion: As the first challenge for PET image reconstruction, PETRIC's solid foundations allow researchers to reuse its framework for evaluating new and existing image reconstruction methods on new or existing datasets. Variant versions of the challenge have and will continue to be launched in the future.

Problem

• Minimizing computational runtime for PET image reconstruction algorithms
• Establishing first challenge for PET image reconstruction evaluation
• Providing open-source framework for algorithm performance assessment

Innovation

• Open-source software for algorithm implementation
• Automated computational framework for evaluation
• Phantom datasets for training and testing